Skip to main content
ZICQ

Skills ZICQ category:Data & Analysis deepstream-dev

Deepstream Dev

NVIDIA DeepStream SDK development with Python pyservicemaker API. Use when building video analytics pipelines, GStreamer-based video processing, TensorRT inference integration, object detection/tracking, or Kafka/message broker integration.

2252 installs

Official URL:skills.sh

What this skill does

Intro in this page language first. The official description stays in its original wording; we do not rewrite SKILL.md.

What it does

NVIDIA DeepStream SDK development with Python pyservicemaker API

When to use it

|

How agents load it

Per Agent Skills progressive disclosure: name and description load at startup (~100 tokens); the full SKILL.md body loads when the skill activates; scripts/, references/, and assets/ load only as needed. This file's sections: DeepStream Development Skill; SDK and Architecture Quick Reference; DeepStream SDK Version Requirements; Typical Pipeline Flow; Memory Model; Critical Rules.

File analysis

File analysis: besides SKILL.md, the body references references/nvinfer_config.md, references/gstreamer_plugins.md, references/service_maker_api.md, references/use_cases_pipelines.md, references/streaming_sources.md, references/kafka_messaging.md. Those resources load on demand.

DeepStream Development SkillSDK and Architecture Quick ReferenceDeepStream SDK Version RequirementsTypical Pipeline FlowMemory ModelCritical RulesKey PathsReference DocumentsQuick Error Reference

· License:CC-BY-4.0 AND Apache-2.0

Source category:skills.sh agent-skill

SKILL.md & Agent activation

Official spec ↗
name
deepstream-dev
description
NVIDIA DeepStream SDK development with Python pyservicemaker API. Use when building video analytics pipelines, GStreamer-based video processing, TensorRT inference integration, object detection/tracking, or Kafka/message broker integration.
License
CC-BY-4.0 AND Apache-2.0
  1. DiscoverThe client exposes names and descriptions to the agent.
  2. ActivateYour request or the task context selects the skill and loads its instructions.
  3. Load resourcesReferenced scripts, documentation and assets are used when needed.
Files referenced by the instructions · 7
  • references/nvinfer_config.md
  • references/gstreamer_plugins.md
  • references/service_maker_api.md
  • references/use_cases_pipelines.md
  • references/streaming_sources.md
  • references/kafka_messaging.md
  • references/best_practices.md

These paths are extracted from the text. Check the upstream package to verify the files exist.

Invocation syntax and available tools depend on your Agent client. Client integration guide ↗

Install this skill

Skills CLI ↗

Choose the target agent and installation scope, keep referenced package files, then verify the skill appears in the client's catalog.

This skill references supporting files. Retrieve the complete directory from the source; copying SKILL.md alone may leave missing dependencies.

Ask your Agent to install

Copy these instructions to a compatible agent and confirm the target directory matches your client.

Install the agent skill "deepstream-dev" into my project. The full SKILL.md and official description are at https://zicq.com/en/skills/skl-79ec3be8b241fe50-Deepstream-Dev.html
Save it as .cursor/skills/deepstream-dev/SKILL.md or .claude/skills/deepstream-dev/SKILL.md and keep the frontmatter name and description exactly as-is.
This skill also ships scripts/, references/, or assets/ — fetch the whole folder from https://github.com/nvidia/skills instead of creating only a SKILL.md.

Full package on GitHub ↗

Install from the terminal · Skills CLI

Requires Node.js and npx. First inspect the repository's skill list to confirm the name.

npx skills add 'https://github.com/nvidia/skills' --list

npx skills add 'https://github.com/nvidia/skills' --skill 'deepstream-dev'

The CLI lets you choose the agent interactively. The default scope is the project; use -g for user scope. Confirm package availability with the discovery command, then use npx skills list to inspect installed skills.

Readable layout
--- name: deepstream-dev description: NVIDIA DeepStream SDK development with Python pyservicemaker API. Use when building video analytics pipelines, GStreamer-based video processing, TensorRT inference integration, object detection/tracking, or Kafka/message broker integration. owner: NVIDIA CORPORATION metadata: author: "NVIDIA CORPORATION " service: deepstream version: 1.1.1 reviewed: 2026-04-24 license: CC-BY-4.0 AND Apache-2.0 --- # DeepStream Development Skill This skill requires access to all of the reference documents listed in the `references/` directory below. Ensure they are available before executing the workflow. When this skill is active, **ALWAYS read the relevant reference documents** before generating code. Do NOT rely on memory - the reference documents contain critical details about exact property names, correct API usage, and common pitfalls. ## SDK and Architecture Quick Reference ### DeepStream SDK Version Requirements - **GStreamer**: 1.24.2 - **NVIDIA Driver**: 590+ - **CUDA**: 13.1 - **TensorRT**: 10.14.1.48 - **Platforms**: Ubuntu 24.04 (x86_64 and ARM64/Jetson) ### Typical Pipeline Flow ```text Source → Stream Muxer → Inference → [Tracker] → OSD → Renderer ``` Components in `[brackets]` are **optional** -- only add them when the user explicitly requests them. | Stage | Role | Key Element(s) | Required? | |-------|------|-----------------|-----------| | Source | Input from files, RTSP, cameras | `nvurisrcbin` (preferred), `nvmultiurisrcbin`, `filesrc` | Yes | | Stream Muxer | Batches streams for inference | `nvstreammux` | Yes | | Inference | TensorRT model execution | `nvinfer`, `nvinferserver` | Yes | | Tracker | Multi-object tracking across frames | `nvtracker` | **Only if requested** | | OSD | Draws bounding boxes, labels, overlays | `nvosdbin` | Yes (for visualization) | | Renderer | Display or save output | `nveglglessink`, `nv3dsink`, `filesink` | Yes | ### Memory Model DeepStream uses NVIDIA Video Memory Manager (NVMM) for zero-copy GPU buffer transfers. Caps strings use `memory:NVMM` to indicate GPU memory (e.g., `video/x-raw(memory:NVMM), format=NV12`). ## Critical Rules 1. **Only Add Requested Components**: Do NOT add pipeline elements the user did not ask for. - **Tracker (`nvtracker`)**: Only add when the user explicitly requests tracking or object IDs across frames - **Secondary GIEs**: Only add when the user requests classification or attribute extraction - **Analytics (`nvdsanalytics`)**: Only add when the user requests line crossing, ROI counting, etc. - **Message broker (`nvmsgbroker`/`nvmsgconv`)**: Only add when the user requests Kafka/cloud messaging - When in doubt, build the **minimal working pipeline** and let the user ask for additions 2. **Default to `nvurisrcbin` for Sources**: When the user says "camera", "stream", "video", or provides a file path: - Always use `nvurisrcbin` -- it handles RTSP, HTTP, and local files (`file://`) transparently - Only use `filesrc` + `qtdemux` + parser when the user explicitly needs raw file source control - For RTSP/live sources, also set `live-source=1` on `nvstreammux` and `sync=0` on the sink - Convert local paths to URI: `"file://" + os.path.abspath(path)` 3. **Metadata Iteration**: Use `.frame_items` and `.object_items` (returns iterators, NOT lists) - NEVER use `len()` on these - iterate to count - Iterator can only be consumed once 4. **Request Pad Syntax**: Use `"sink_%u"` template, NEVER literal pad names ```python pipeline.link(("decoder", "mux"), ("", "sink_%u")) # CORRECT # pipeline.link(("decoder", "mux"), ("", "sink_0")) # WRONG - will fail ``` 5. **Platform Detection for Sinks**: ```python import platform sink_type = "nv3dsink" if platform.processor() == "aarch64" else "nveglglessink" ``` - For WSL2 Ubuntu 24 Docker, this default selection must be overridden. - **WSL2 + Ubuntu 24 Docker**: If `/proc/version` contains `microsoft` or `wsl` and `/etc/os-release` has `VERSION_ID="24.04"`, the generated app must never create a display branch or display sink (`nveglglessink`, `nv3dsink`, etc.), even if the prompt asks for display. Do not rely on a `--no-display` flag for this case. Generate encoded MP4 output only (`nvv4l2h264enc` -> `h264parse` -> `mp4mux`/`qtmux` -> `filesink`) and make the default run path write the annotated video file. In the generated `README.md`, explicitly explain that WSL2 Ubuntu 24 Docker is MP4-output-only because display sinks are disabled by a known issue. If the user explicitly requested display, add an inline code comment and README note explaining: `Display requested but disabled due to WSL2 Ubuntu 24 Docker limitation — MP4 output generated instead.` - **Non-WSL targets**: Do not add WSL-specific behavior or WSL limitation text to generated apps or READMEs. Use the normal platform display sink selection above. 6. **Buffer Cloning**: Always clone buffers for async processing ```python tensor = buffer.extract(0).clone() # CRITICAL ``` 7. **Queue Types**: - `queue.Queue` → Use with `threading.Thread` - `multiprocessing.Queue` → Use with `multiprocessing.Process` - Using wrong type causes silent data loss! 8. **nvinfer Config Format**: - YAML: Use `property:` section (NOT `model:`), `key: value` with space after colon - INI: Use `[property]` section, `key=value` with equals sign - Section MUST be named `property` 9. **nvmsgbroker is a SINK**: Cannot have downstream elements - use `tee` to split pipeline 10. **ALL Sinks Need async=0 for Tee Splits or Dynamic Sources**: CRITICAL for state transitions ```python # When using tee splits OR dynamic sources, ALL sinks MUST have async=0 pipeline.add("nveglglessink", "sink", { "sync": 0, "qos": 0, "async": 0 # CRITICAL - prevents state transition deadlock }) ``` **Symptom if missing**: Pipeline stays in PAUSED state, no video displays. 11. **Built-in Probe Attachment**: `measure_fps_probe` can only be attached to processing elements (e.g., `nvinfer`, `nvosdbin`), **NOT** to sink elements. Attaching to a sink raises `RuntimeError: Probe failure`. 12. **Dynamic ONNX Models Require `infer-dims`**: When the ONNX model has dynamic input shapes (e.g., exported with `dynamic=True` in Ultralytics YOLO, or with dynamic batch/height/width axes), you **MUST** add `infer-dims=C;H;W` to the nvinfer config. Without it, TensorRT sees `-1` for dynamic dimensions and fails with `setDimensions: Error Code 3`. Common values: - YOLO models (640 input): `infer-dims=3;640;640` - Models with 416 input: `infer-dims=3;416;416` - Models with 1280 input: `infer-dims=3;1280;1280` 13. **Ultralytics YOLO Output Format Depends on Model Generation** — newer models (v10+/v26+) output post-NMS results; older models (v8/v11) output raw pre-NMS tensors. The custom parser and `cluster-mode` **must** match the actual output: | Model generation | Output tensor shape | Fields | `cluster-mode` | |------------------|--------------------|---------------------------------|----------------| | v8 / v11 | `[batch, 84, 8400]` | `[features(4+80), anchors]` — raw cx/cy/w/h + class scores, no NMS | `2` (NMS) | | v10 / v26+ | `[batch, 300, 6]` | `[max_det, (x1,y1,x2,y2,conf,cls)]` — already post-NMS, pixel coords | `4` (none) | **How to identify at runtime**: log `inferDims.d[0]` and `inferDims.d[1]` inside the custom parser. - `d={84, 8400}` → pre-NMS (v8/v11 style) - `d={300, 6}` → post-NMS (v10/v26+ style) **Symptom of mismatch**: If `cluster-mode: 2` is used with a post-NMS `[N, 6]` output, bounding boxes appear shifted by 45° or 135° from the actual objects (DeepStream's NMS incorrectly re-processes already-final coordinates). If you see tilted or rotated boxes, also check the OBB / `rotation_angle` note in `references/nvinfer_config.md`: for non-OBB models, value-initialize `NvDsInferObjectDetectionInfo` with `obj{}` and keep `rotation_angle = 0`; plain `NvDsInferObjectDetectionInfo obj;` leaves fields uninitialized. 14. **Virtual Environment Must Include pyservicemaker**: `pyservicemaker` is installed system-wide but is NOT accessible from a standard Python virtual environment. When a task requires a venv (e.g., for model download/conversion pip dependencies), **always install `pyservicemaker` and `pyyaml` inside the venv**; do not rewrite pyservicemaker pipeline code into non-pyservicemaker code to work around a missing import. The venv setup in generated code and README must always include: ```bash python3 -m venv venv source venv/bin/activate pip install /opt/nvidia/deepstream/deepstream/service-maker/python/pyservicemaker*.whl pyyaml pip install -r requirements.txt # other dependencies ``` **Symptom if missing**: `ModuleNotFoundError: No module named 'pyservicemaker'` when running the app inside the venv. ## Key Paths - Models: `/opt/nvidia/deepstream/deepstream/samples/models/` - Primary Detector: `/opt/nvidia/deepstream/deepstream/samples/models/Primary_Detector/resnet18_trafficcamnet_pruned.onnx` - Tracker lib: `/opt/nvidia/deepstream/deepstream/lib/libnvds_nvmultiobjecttracker.so` - Kafka lib: `/opt/nvidia/deepstream/deepstream/lib/libnvds_kafka_proto.so` - Sample configs: `/opt/nvidia/deepstream/deepstream/samples/configs/deepstream-app/` ## Reference Documents **IMPORTANT**: Always read these documents for complete details. Do NOT generate code from memory. | Document | Use When | |----------|----------| | [references/gstreamer_plugins.md](references/gstreamer_plugins.md) | Looking up plugin properties, ALL properties listed | | [references/service_maker_api.md](references/service_maker_api.md) | Using Pipeline/Flow API, metadata access, probes, EventMessageUserMetadata | | [references/use_cases_pipelines.md](references/use_cases_pipelines.md) | Building pipelines: simple playback, multi-inference, cascaded GIE | | [references/streaming_sources.md](references/streaming_sources.md) | Ingesting local files, HTTP MP4, HLS, MPEG-DASH, or RTSP sources with nvurisrcbin | | [references/kafka_messaging.md](references/kafka_messaging.md) | Kafka/message broker setup, nvmsgconv/nvmsgbroker config, msg2p-newapi | | [references/best_practices.md](references/best_practices.md) | Design patterns, common pitfalls, anti-patterns | | [references/buffer_apis.md](references/buffer_apis.md) | BufferProvider/Feeder (injection), BufferRetriever/Receiver (extraction) | | [references/media_extractor_advanced.md](references/media_extractor_advanced.md) | MediaExtractor, MediaChunk, FrameSampler | | [references/utilities_config.md](references/utilities_config.md) | PerfMonitor, EngineFileMonitor, SourceConfig, SensorInfo, SmartRecordConfig | | [references/nvinfer_config.md](references/nvinfer_config.md) | nvinfer config file format, ALL parameters | | [references/tracker_config.md](references/tracker_config.md) | nvtracker config, NvDCF/IOU/DeepSORT/NvSORT | | [references/troubleshooting.md](references/troubleshooting.md) | Error messages and solutions | | [references/rest_api_dynamic.md](references/rest_api_dynamic.md) | REST API, dynamic source add/remove, nvmultiurisrcbin | | [references/metamux_config.md](references/metamux_config.md) | nvdsmetamux config, parallel multi-model inference, metadata merging, source ID filtering | | [references/docker_containers.md](references/docker_containers.md) | Docker images, Dockerfile examples, pyservicemaker install, container run commands | | [references/nvds_msgapi_adapter.md](references/nvds_msgapi_adapter.md) | Building custom protocol adapters: nvds_msgapi | ## Quick Error Reference | Error | Solution | |-------|----------| | `iterator has no len()` | Iterate to count, don't use `len()` | | `pad template not found` | Use `"sink_%u"` not `"sink_0"` | | Queue data loss | Use `multiprocessing.Queue` with `Process` | | Config parse failed | Use `property:` not `model:` in YAML | | `is-classifier` deprecation warning | Use `network-type: 1` instead of `is-classifier: 1` for classifiers; omit both for detectors | | `min-boxes` unknown key warning | Use `minBoxes` (camelCase) in `class-attrs-*` sections, not `min-boxes` | | Secondary GIE inactive | Set `process-mode: 2`, check `operate-on-gie-id` | | Tee/dynamic source stuck PAUSED | Set `async: 0` on **ALL** sink elements | | WSL2 Ubuntu 24 display sink requested | Do not use display sinks due to a known bug; write MP4 with `filesink` and document the WSL limitation in README | | RTSP no data/reconnecting | Test URL with ffplay, check credentials | | `RuntimeError: Probe failure` | `measure_fps_probe` cannot attach to sink elements; use `nvinfer` or `nvosdbin` instead | | `setDimensions` negative dims / engine build failed | Add `infer-dims=C;H;W` for dynamic ONNX models (e.g., `infer-dims=3;640;640`) | | `No module named 'pyservicemaker'` in venv | `pip install /opt/nvidia/deepstream/deepstream/service-maker/python/pyservicemaker*.whl pyyaml` inside the venv | | `AttributeError: object has no attribute 'obj_label'` | Use `obj_meta.label` not `obj_meta.obj_label` in pyservicemaker (C API name differs from Python binding) |

Related skills

Data & Analysis

Marketing Skills

TL;DR: 23 marketing playbooks (CRO, SEO, copy, analytics, experiments, pricing, launches, ads, social). Use to get checklists + copy/paste d…

Data & Analysis

Crypto & Stock Market Data (Node.js)

No API KEY needed for free tier. Professional-grade cryptocurrency and stock market data integration for real-time prices, company profiles,…

Data & Analysis

Azure Storage

Azure Storage Services including Blob Storage, File Shares, Queue Storage, Table Storage, and Data Lake. Answers questions about storage acc…

Data & Analysis

Azure Kusto

Query and analyze data in Azure Data Explorer (Kusto/ADX) using KQL for log analytics, telemetry, and time series analysis. WHEN: KQL querie…